cjwbw / analog-diffusion

a dreambooth model trained on a diverse set of analog photographs

  • Public
  • 234.4K runs
  • A100 (80GB)

Input

string
Shift + Return to add a new line

Input prompt

Default: "analog style closeup portrait of cowboy George Washington"

string
Shift + Return to add a new line

The prompt or prompts not to guide the image generation (what you do not want to see in the generation). Ignored when not using guidance.

Default: "blur haze"

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

integer

Number of images to output

Default: 1

integer
(minimum: 1, maximum: 500)

Number of denoising steps

Default: 20

number
(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7

string

Choose a scheduler.

Default: "K_EULER_ANCESTRAL"

integer

Random seed. Leave blank to randomize the seed

Output

output
Generated in

Run time and cost

This model costs approximately $0.0065 to run on Replicate, or 153 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 5 seconds. The predict time for this model varies significantly based on the inputs.

Readme

weights from: https://huggingface.co/wavymulder/Analog-Diffusion

Analog Diffusion Header

In your prompt, use the activation token: analog style

You may need to use the words blur haze naked in your negative prompts. My dataset did not include any NSFW material but the model seems to be pretty horny. Note that using blur and haze in your negative prompt can give a sharper image but also a less pronounced analog film effect.

Trained from 1.5 with VAE.

Environments Example Characters Example

Here’s a link to non-cherrypicked batches.